Activation on the Move: Adaptive Information Retrieval via Spreading Activation
نویسنده
چکیده
With the increasing amount of information available on the Internet one of the most challenging tasks is to provide search interfaces that are easy to use without having to learn a specific syntax. In this thesis a query interface exploiting the intuitiveness of natural language for accessing tourism information is presented. Furthermore, the results and insights from analyzing the natural language queries collected during a field trial in which the interface was promoted via the homepage of the largest Austrian tourism platform Tiscover are described. This analysis shows how users formulate queries when their imagination is not limited by conventional search interfaces with structured forms consisting of check boxes, radio buttons and special-purpose text fields. In a usability study subjects were asked to identify themselves with predefined tourism related scenarios. Subsequently, they had to accomplish the tasks described in these scenarios. On the one hand, subjects were requested to use the standard Tiscover interface to fulfill the stipulated tasks, and on the other hand, they were asked to use the natural language interface to retrieve results. The experiences users made during the interaction with the interfaces have been observed and the findings are presented herein. The major concern of this thesis is the development of a knowledge representation model based on a network structure as motivated by the results of a field trial and a usability study. In particular, an approach based on associative networks, for defining semantic relationships of terms is presented. More precisely, the relatedness of terms is taken into account and it is shown,
منابع مشابه
An Adaptive Information Retrieval System Based on Associative Networks
In this paper we present a multilingual information retrieval system that provides access to Tourism information by exploiting the intuitiveness of natural language. In particular, we describe the knowledge representation model underlying the information retrieval system. This knowledge representation approach is based on associative networks and allows the definition of semantic relationships ...
متن کاملBiologically Motivated Distributed Designs for Adaptive Knowledge Management
2 The main abbreviations used in this article in addition to DIS are: IR (Information Retrieval), SA (Spreading Activation), and ARP (Active Recommendation Project). Luis Mateus Rocha and Johan Bollen Los Alamos National Laboratory, MS B256 MS B362 Los Alamos, NM 87545, USA E-Mail: [email protected] or † [email protected], [email protected] WWW: http://www.c3.lanl.gov/~rocha , http://www.c3.lanl.go...
متن کاملA Spreading Activation Framework for Ontology-Enhanced Adaptive Information Access within Organisations
This research investigates a unique Indexing Structure and Navigational Interface which integrates (1) ontology-driven knowledge-base (2) statistically derived indexing parameters, and (3) experts' feedback into a single Spreading Activation Framework to harness knowledge from heterogeneous knowledge assets. Within an organisation, organisational ontologies capture precise knowledge about organ...
متن کاملReliefs: un système d'inspiration cognitive pour le filtrage adaptatif de documents textuels
This paper deals with the description of a new adaptive filtering system called RELIEFS (for RELevance Information Fuzzy System). The main principles of this system draw their inspiration from cognitive models of information selection. More precisely, our research is based on the analysis of semantic memory models (knowledge access and knowledge organisation) and attentional models (information...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2003